End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE QNLI
       type: glue
       config: qnli
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7752150832875709
+      value: 0.8112758557569101
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_qnli
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7668
-- Accuracy: 0.7752
+- Loss: 0.4198
+- Accuracy: 0.8113
 
 ## Model description
 

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 8.0,
     "eval_accuracy": 0.8112758557569101,
     "eval_loss": 0.4198276698589325,
-    "eval_runtime": 6.7804,
+    "eval_runtime": 6.929,
     "eval_samples": 5463,
-    "eval_samples_per_second": 805.699,
-    "eval_steps_per_second": 3.245,
+    "eval_samples_per_second": 788.425,
+    "eval_steps_per_second": 3.175,
     "train_loss": 0.3110694268854653,
-    "train_runtime": 3241.717,
+    "train_runtime": 3314.8577,
     "train_samples": 104743,
-    "train_samples_per_second": 1615.548,
-    "train_steps_per_second": 6.324
+    "train_samples_per_second": 1579.902,
+    "train_steps_per_second": 6.184
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 8.0,
     "eval_accuracy": 0.8112758557569101,
     "eval_loss": 0.4198276698589325,
-    "eval_runtime": 6.7804,
+    "eval_runtime": 6.929,
     "eval_samples": 5463,
-    "eval_samples_per_second": 805.699,
-    "eval_steps_per_second": 3.245
+    "eval_samples_per_second": 788.425,
+    "eval_steps_per_second": 3.175
 }

logs/events.out.tfevents.1677741436.serv-9223.249682.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a64a5049a532d3d11d048a540f7cad0ae6f116874278fa8d3375b1379f197d
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 8.0,
     "train_loss": 0.3110694268854653,
-    "train_runtime": 3241.717,
+    "train_runtime": 3314.8577,
     "train_samples": 104743,
-    "train_samples_per_second": 1615.548,
-    "train_steps_per_second": 6.324
+    "train_samples_per_second": 1579.902,
+    "train_steps_per_second": 6.184
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.6873512721947648,
       "eval_loss": 0.5954663157463074,
-      "eval_runtime": 6.817,
-      "eval_samples_per_second": 801.373,
-      "eval_steps_per_second": 3.227,
+      "eval_runtime": 6.9854,
+      "eval_samples_per_second": 782.059,
+      "eval_steps_per_second": 3.149,
       "step": 410
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_accuracy": 0.794801391177009,
       "eval_loss": 0.44860708713531494,
-      "eval_runtime": 6.81,
-      "eval_samples_per_second": 802.199,
-      "eval_steps_per_second": 3.231,
+      "eval_runtime": 6.9353,
+      "eval_samples_per_second": 787.714,
+      "eval_steps_per_second": 3.172,
       "step": 820
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_accuracy": 0.8112758557569101,
       "eval_loss": 0.4198276698589325,
-      "eval_runtime": 6.8165,
-      "eval_samples_per_second": 801.434,
-      "eval_steps_per_second": 3.227,
+      "eval_runtime": 6.9396,
+      "eval_samples_per_second": 787.224,
+      "eval_steps_per_second": 3.17,
       "step": 1230
     },
     {
@@ -62,9 +62,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.7865641588870584,
       "eval_loss": 0.48407182097435,
-      "eval_runtime": 6.8451,
-      "eval_samples_per_second": 798.094,
-      "eval_steps_per_second": 3.214,
+      "eval_runtime": 6.9525,
+      "eval_samples_per_second": 785.765,
+      "eval_steps_per_second": 3.164,
       "step": 1640
     },
     {
@@ -77,9 +77,9 @@
       "epoch": 5.0,
       "eval_accuracy": 0.790591250228812,
       "eval_loss": 0.5340340733528137,
-      "eval_runtime": 6.828,
-      "eval_samples_per_second": 800.093,
-      "eval_steps_per_second": 3.222,
+      "eval_runtime": 6.9383,
+      "eval_samples_per_second": 787.374,
+      "eval_steps_per_second": 3.171,
       "step": 2050
     },
     {
@@ -92,9 +92,9 @@
       "epoch": 6.0,
       "eval_accuracy": 0.7728354384038074,
       "eval_loss": 0.6281628608703613,
-      "eval_runtime": 6.835,
-      "eval_samples_per_second": 799.265,
-      "eval_steps_per_second": 3.219,
+      "eval_runtime": 6.9508,
+      "eval_samples_per_second": 785.951,
+      "eval_steps_per_second": 3.165,
       "step": 2460
     },
     {
@@ -107,9 +107,9 @@
       "epoch": 7.0,
       "eval_accuracy": 0.7752150832875709,
       "eval_loss": 0.6678447723388672,
-      "eval_runtime": 6.8476,
-      "eval_samples_per_second": 797.793,
-      "eval_steps_per_second": 3.213,
+      "eval_runtime": 6.9465,
+      "eval_samples_per_second": 786.441,
+      "eval_steps_per_second": 3.167,
       "step": 2870
     },
     {
@@ -122,9 +122,9 @@
       "epoch": 8.0,
       "eval_accuracy": 0.7752150832875709,
       "eval_loss": 0.7668098211288452,
-      "eval_runtime": 6.8357,
-      "eval_samples_per_second": 799.183,
-      "eval_steps_per_second": 3.218,
+      "eval_runtime": 6.9539,
+      "eval_samples_per_second": 785.607,
+      "eval_steps_per_second": 3.164,
       "step": 3280
     },
     {
@@ -132,9 +132,9 @@
       "step": 3280,
       "total_flos": 1.0584157486002995e+17,
       "train_loss": 0.3110694268854653,
-      "train_runtime": 3241.717,
-      "train_samples_per_second": 1615.548,
-      "train_steps_per_second": 6.324
+      "train_runtime": 3314.8577,
+      "train_samples_per_second": 1579.902,
+      "train_steps_per_second": 6.184
     }
   ],
   "max_steps": 20500,